Tom St Denis [Thu, 14 Sep 2017 12:57:26 +0000 (08:57 -0400)]
drm/amd/amdgpu: Support VM environments in amdgpu_ttm_access_memory()
Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/radeon: properly initialize r600_audio_status() data
The structure returned from r600_audio_status() is only partially
initialized, and older gcc versions (4.3 and 4.4) warn about this:
drivers/gpu/drm/radeon/r600_hdmi.c: In function 'r600_audio_status':
drivers/gpu/drm/radeon/r600_hdmi.c:108: error: 'status.id' is used uninitialized in this function
drivers/gpu/drm/radeon/r600_hdmi.c:108: error: 'status.connected' is used uninitialized in this function
drivers/gpu/drm/radeon/r600_hdmi.c:108: error: 'status.offset' is used uninitialized in this function
This is harmless and surprisingly correct in C99, as the caller
only accesses the fields that got initialized, so newer compilers
don't warn about it, but initializing the entire structure feels
like the right thing to do here and avoids the warning.
Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tom St Denis [Wed, 13 Sep 2017 16:35:15 +0000 (12:35 -0400)]
drm/amd/amdgpu: Change vram debugfs to NO_KIQ for VM environments
Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Wed, 13 Sep 2017 08:43:09 +0000 (10:43 +0200)]
drm/ttm: fix memory leak while individualizing BOs
We need to free the reservation object before we take the BO
from the delayed delete list.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Monk Liu <monk.liu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Tue, 12 Sep 2017 08:56:17 +0000 (10:56 +0200)]
drm/amdgpu: fix and cleanup amdgpu_bo_create v2
We adjusted the BO flags for USWC handling, but those never took effect
because the placement was passed in instead of generated inside this
function.
v2: better commit message
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Mon, 11 Sep 2017 15:10:26 +0000 (17:10 +0200)]
drm/amd: remove min/max addr handling from cgs
Nobody is actually using this and it causes a bunch of unused and buggy code.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Mon, 11 Sep 2017 13:51:30 +0000 (15:51 +0200)]
drm/amdgpu: fix cgs alignment handling
This always allocated on PAGE_SIZE alignment.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Michel Dänzer [Mon, 11 Sep 2017 08:09:17 +0000 (17:09 +0900)]
radeon: Only destroy fbdev framebuffer if it was initialized
Fixes crash when trying to unload the radeon module before the fbdev
framebuffer was initialized, which can happen since the DRM fbdev helper
code supports deferred setup.
Acked-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Michel Dänzer <michel.daenzer@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Michel Dänzer [Mon, 11 Sep 2017 08:04:41 +0000 (17:04 +0900)]
amdgpu: Only destroy fbdev framebuffer if it was initialized
Fixes crash when trying to unload the amdgpu module before the fbdev
framebuffer was initialized, which can happen since the DRM fbdev helper
code supports deferred setup.
Acked-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Michel Dänzer <michel.daenzer@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tom St Denis [Tue, 12 Sep 2017 16:29:06 +0000 (12:29 -0400)]
drm/amd/powerplay: lock grbm_gfx index when changing instance
Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tom St Denis [Tue, 12 Sep 2017 14:05:48 +0000 (10:05 -0400)]
drm/amd/powerplay: Tidy up smu7_enable_didt()
Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tom St Denis [Tue, 12 Sep 2017 14:01:34 +0000 (10:01 -0400)]
drm/amd/powerplay: Make use of PP_CAP in smu7_powertune.c
Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tom St Denis [Tue, 12 Sep 2017 13:56:45 +0000 (09:56 -0400)]
drm/amd/powerplay: Remove unneeded return from pp_smu7_thermal_fini()
Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tom St Denis [Tue, 12 Sep 2017 13:53:25 +0000 (09:53 -0400)]
drm/amd/powerplay: Make use of PP_CAP in smu7_thermal.c
Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tom St Denis [Tue, 12 Sep 2017 13:51:36 +0000 (09:51 -0400)]
drm/amd/powerplay: Tidy up smu7_fan_ctrl_get_fan_speed_rpm()
Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tom St Denis [Tue, 12 Sep 2017 13:46:40 +0000 (09:46 -0400)]
drm/amd/powerplay: Tidy up smu7_fan_ctrl_get_fan_speed_info()
Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Mon, 11 Sep 2017 14:54:59 +0000 (16:54 +0200)]
drm/amdgpu: fix amdgpu_vm_handle_moved as well v2
There is no guarantee that the last BO_VA actually needed an update.
Additional to that all command submissions must wait for moved BOs to
be cleared, not just the first one.
v2: Don't overwrite any newer fence.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Fri, 8 Sep 2017 12:09:41 +0000 (14:09 +0200)]
drm/amdgpu: fix VM sync with always valid BOs v2
All users of a VM must always wait for updates with always
valid BOs to be completed.
v2: remove debugging leftovers, rename struct member
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Roger He <Hongbo.He@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Evan Quan [Mon, 4 Sep 2017 09:48:27 +0000 (17:48 +0800)]
drm/amdgpu: enable raven to load firmwares by psp at default (v2)
- v2: share code with CHIP_VEGA10 case
Signed-off-by: Evan Quan <evan.quan@amd.com> Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Reviewed-by: Huang Rui <ray.huang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Evan Quan [Fri, 8 Sep 2017 05:09:50 +0000 (13:09 +0800)]
drm/amdgpu: stop psp ring on suspend
Otherwise, the ring will fail to create on next resume.
Signed-off-by: Evan Quan <evan.quan@amd.com> Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Reviewed-by: Huang Rui <ray.huang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Evan Quan [Fri, 8 Sep 2017 05:04:52 +0000 (13:04 +0800)]
drm/amdgpu: added api for stopping psp ring (v2)
- v2: reuse the ring stop api in ring destory
Signed-off-by: Evan Quan <evan.quan@amd.com> Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Reviewed-by: Huang Rui <ray.huang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Evan Quan [Mon, 4 Sep 2017 09:42:28 +0000 (17:42 +0800)]
drm/amdgpu: fixed raven psp cmd prepare and submit
- fw_size in psp_v10_0_prep_cmd_buf is wrongly set as 0
- fixed the wrong calculation of psp_write_ptr_reg in psp_v10_0_cmd_submit
Signed-off-by: Evan Quan <evan.quan@amd.com> Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Reviewed-by: Huang Rui <ray.huang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Tue, 12 Sep 2017 18:29:07 +0000 (14:29 -0400)]
drm/amdgpu: move MMU notifier related defines to amdgpu_mn.h
Just some cleanup.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Michel Dänzer <michel.daenzer@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Fri, 8 Sep 2017 15:19:19 +0000 (17:19 +0200)]
drm/amdgpu: move amdgpu_ttm_tt_* declarations into amdgpu_ttm.h
Just some cleanup.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Michel Dänzer <michel.daenzer@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Tue, 5 Sep 2017 15:30:46 +0000 (17:30 +0200)]
drm/amdgpu: keep the MMU lock until the update ends v4
This is quite controversial because it adds another lock which is held during
page table updates, but I don't see much other option.
v2: allow multiple updates to be in flight at the same time
v3: simplify the patch, take the read side only once
v4: correctly fix rebase conflict
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Tue, 12 Sep 2017 18:25:14 +0000 (14:25 -0400)]
drm/amdgpu: stop reserving the BO in the MMU callback v3
Instead take the callback lock during the final parts of CS.
This should solve the last remaining locking order problems with BO reservations.
v2: rebase, make dummy functions static inline
v3: add one more missing inline and comments
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Tue, 5 Sep 2017 12:50:24 +0000 (14:50 +0200)]
drm/amdgpu: use a rw_semaphore for MMU notifiers
Allow at least some parallel processing.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Tue, 5 Sep 2017 12:36:44 +0000 (14:36 +0200)]
drm/amdgpu: move userptr BOs to CPU domain during CS v2
Instead of moving them in the MMU notifier move them during CS.
v2: still mark pages as accessed/dirty
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> (v1) Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Tue, 5 Sep 2017 12:30:05 +0000 (14:30 +0200)]
drm/amdgpu: stop using BO status for user pages
Instead use a counter to figure out if we need to set new pages or not.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Sun, 3 Sep 2017 13:22:06 +0000 (15:22 +0200)]
drm/amdgpu: move taking mmap_sem into get_user_pages v2
This didn't helped as intended, just simplify the code.
v2: unlock mmap_sem in the error path as well
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Bas Nieuwenhuizen [Thu, 7 Sep 2017 11:23:21 +0000 (13:23 +0200)]
drm/amdgpu: Account for shadow PTs in mapping update IB size.
When amdgpu_vm_frag_ptes calls amdgpu_vm_update_ptes and the pt
has a shadow PT we mirror all the write to the shadow PT too, which
results in twice the commands.
Signed-off-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Mon, 4 Sep 2017 18:58:45 +0000 (20:58 +0200)]
drm/ttm: fix ttm_bo_cleanup_refs_or_queue once more
With shared reservation objects __ttm_bo_reserve() can easily fail even on
destroyed BOs. This prevents correct handling when we need to individualize
the reservation object.
Fix this by individualizing the object before even trying to reserve it.
Signed-off-by: Christian König <christian.koenig@amd.com> Acked-by: Chunming Zhou <david1.zhou@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The patch doesn't work at all:
1. The CS can still be blocked because of amdgpu_ctx_add_fence().
2. The order of submission isn't correct any more.
3. We could end up using freed up memory because we now drop the
ctx reference to early.
This needs to be fixed cleanly by doing the context handling after the BO
handling, but this is a larger task just avoid the obvious crashes for now.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Monk Liu monk.liu@amd.com Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Sat, 2 Sep 2017 11:21:31 +0000 (13:21 +0200)]
drm/amdgpu: fix userptr put_page handling
Move calling put_page into the unpopulate callback. Otherwise we mess up the pages
reference count when it is unbound multiple times.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tom St Denis [Tue, 5 Sep 2017 11:30:59 +0000 (07:30 -0400)]
drm/ttm: Fix configuration error around populate_and_map() functions
Fixed kbuild errors when IOMMU/SWIOTLB are disabled.
Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Rex Zhu [Tue, 29 Aug 2017 08:08:56 +0000 (16:08 +0800)]
drm/amd/powerplay: add UMD P-state in powerplay.
This feature is for UMD to run benchmark in a
power state that is as steady as possible. kmd
need to fix the power state as stable as possible.
now, kmd support four level:
profile_standard,peak,min_sclk,min_mclk
move common related code to amd_powerplay.c
Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The header comment in include/trace/define_trace.h specifies that the
TRACE_INCLUDE_PATH needs to be relative to the define_trace.h header
rather than the trace file including it. Most instances get that wrong
and work around it by adding the $(src) directory to the include path.
While this works, it is preferable to refer to the correct path to the
trace file in the first place and avoid any workaround.
Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Thierry Reding <treding@nvidia.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The header comment in include/trace/define_trace.h specifies that the
TRACE_INCLUDE_PATH needs to be relative to the define_trace.h header
rather than the trace file including it. Most instances get that wrong
and work around it by adding the $(src) directory to the include path.
While this works, it is preferable to refer to the correct path to the
trace file in the first place and avoid any workaround.
Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Thierry Reding <treding@nvidia.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tom St Denis [Fri, 1 Sep 2017 16:52:38 +0000 (12:52 -0400)]
drm/ttm: Fix trace include path (v2)
Reviewed-by: Thierry Reding <treding@nvidia.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(v2): Drop Makefile change too.
Tom St Denis [Fri, 1 Sep 2017 13:55:04 +0000 (09:55 -0400)]
drm/amd/amdgpu: Cleanup gmc_v9_0_suspend()
Even though fini returns 0 always it could theoretically
fail in the future. Might as well return it instead of 0.
Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tom St Denis [Fri, 1 Sep 2017 13:53:44 +0000 (09:53 -0400)]
drm/amd/amdgpu: Tidy up gmc_v9_0_hw_init()
Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tom St Denis [Fri, 1 Sep 2017 13:52:21 +0000 (09:52 -0400)]
drm/amd/amdgpu: Tidy up gmc_v9_0_gart_enable()
Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tom St Denis [Fri, 1 Sep 2017 13:13:04 +0000 (09:13 -0400)]
drm/amd/amdgpu: Support full range of GFX ring names
Right now there's only one but the rest of the code is being
setup to support more so might as well fix this up too.
Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Fri, 1 Sep 2017 07:22:56 +0000 (09:22 +0200)]
drm/amdgpu: fix placement flags in amdgpu_ttm_bind
Otherwise we lose the NO_EVICT flag and can try to evict pinned BOs.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Fri, 1 Sep 2017 12:46:19 +0000 (14:46 +0200)]
drm/amdgpu: fix moved list handling in the VM
Only move BOs to the moved/relocated list when they aren't already on a list.
This prevents accidential removal from the evicted list.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Roger He [Wed, 30 Aug 2017 05:01:19 +0000 (13:01 +0800)]
drm/amdgpu: handle all fragment sizes v4
This can improve performance for some cases.
v2 (chk): handle all sizes, simplify the patch quite a bit
v3 (chk): adjust dw estimation as well
v4 (chk): use single loop, make end mask 64bit
Signed-off-by: Roger He <Hongbo.He@amd.com> Signed-off-by: Christian König <christian.koenig@amd.com> Tested-by: Roger He <Hongbo.He@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tom St Denis [Thu, 31 Aug 2017 13:48:11 +0000 (09:48 -0400)]
drm/amd/amdgpu: Simplify gfx_v9_0_wait_for_idle()
Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tom St Denis [Thu, 31 Aug 2017 13:43:47 +0000 (09:43 -0400)]
drm/amd/amdgpu: Fix indentation in gfx_v9_0_mqd_init()
Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tom St Denis [Thu, 31 Aug 2017 13:40:38 +0000 (09:40 -0400)]
drm/amd/amdgpu: Tidy up gfx_v9_0_rlc_stop()
Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tom St Denis [Thu, 31 Aug 2017 13:31:23 +0000 (09:31 -0400)]
drm/amd/amdgpu: Tidy up gfx_v9_0_enable_gfx_dynamic_mg_power_gating()
Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tom St Denis [Thu, 31 Aug 2017 13:31:01 +0000 (09:31 -0400)]
drm/amd/amdgpu: Tidy up gfx_v9_0_enable_gfx_static_mg_power_gating()
Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tom St Denis [Thu, 31 Aug 2017 13:27:22 +0000 (09:27 -0400)]
drm/amd/amdgpu: Tidy up gfx_v9_0_enable_gfx_pipeline_powergating()
Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tom St Denis [Thu, 31 Aug 2017 13:14:41 +0000 (09:14 -0400)]
drm/amd/amdgpu: Tidy up gfx_v9_0_enable_gfx_cg_power_gating()
Make it consistent in style with the other CG/PG enable functions...
Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tom St Denis [Thu, 31 Aug 2017 13:12:47 +0000 (09:12 -0400)]
drm/amd/amdgpu: Tidy up gfx_v9_0_enable_cp_power_gating()
Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tom St Denis [Thu, 31 Aug 2017 13:02:33 +0000 (09:02 -0400)]
drm/amd/amdgpu: Tidy up gfx_v9_0_enable_sck_slow_down_on_power_down()
Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tom St Denis [Thu, 31 Aug 2017 13:01:11 +0000 (09:01 -0400)]
drm/amd/amdgpu: Tidy up gfx_v9_0_enable_sck_slow_down_on_power_up()
Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tom St Denis [Thu, 31 Aug 2017 12:59:00 +0000 (08:59 -0400)]
drm/amd/amdgpu: Tidy up gfx_v9_0_enable_save_restore_machine()
Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tom St Denis [Thu, 31 Aug 2017 12:50:23 +0000 (08:50 -0400)]
drm/amd/amdgpu: Tidy up gfx_v9_0_ngg_en()
Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Tom St Denis [Thu, 31 Aug 2017 12:41:54 +0000 (08:41 -0400)]
drm/amd/amdgpu: Tidy up register list formatting.
Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Tue, 29 Aug 2017 14:14:32 +0000 (16:14 +0200)]
drm/amdgpu: bump version for support of local BOs
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Fri, 25 Aug 2017 07:14:43 +0000 (09:14 +0200)]
drm/amdgpu: add IOCTL interface for per VM BOs v3
Add the IOCTL interface so that applications can allocate per VM BOs.
Still WIP since not all corner cases are tested yet, but this reduces average
CS overhead for 10K BOs from 21ms down to 48us.
v2: add some extra checks, remove the WIP tag
v3: rename new flag to AMDGPU_GEM_CREATE_VM_ALWAYS_VALID
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Wed, 16 Aug 2017 09:13:48 +0000 (11:13 +0200)]
drm/amdgpu: add support for per VM BOs v2
Per VM BOs are handled like VM PDs and PTs. They are always valid and don't
need to be specified in the BO lists.
v2: validate PDs/PTs first
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Tue, 29 Aug 2017 14:07:31 +0000 (16:07 +0200)]
drm/amdgpu: restrict userptr even more
Don't allow them to be GEM imported into another process.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Chunming Zhou <david1.zhou@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Thu, 31 Aug 2017 08:46:20 +0000 (10:46 +0200)]
drm/amdgpu: fix new PD update code for Vega10 v2
We need to refer to the parent instead of the root BO for multi
level page tables on Vega10. Also don't set the PDE_PTE bit.
v2: Don't set the PDE_PTE bit either.
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-and-Tested-by: Roger He <Hongbo.He@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Thu, 8 Jun 2017 09:15:16 +0000 (11:15 +0200)]
drm/amdgpu: move hw generation check into amdgpu_doorbell_init v2
This way we can safely call it on SI as well.
v2: fix type in commit message
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
projects / users / dwmw2 / linux.git / log